degenRobot
commited on
Commit
•
da45da2
1
Parent(s):
da827df
Update README.md
Browse files
README.md
CHANGED
@@ -21,8 +21,11 @@ This model is an experimental fine tune of LLama-3
|
|
21 |
|
22 |
## Datasets used:
|
23 |
|
24 |
-
-
|
25 |
-
-
|
|
|
|
|
|
|
26 |
|
27 |
### Model Description
|
28 |
|
@@ -42,4 +45,7 @@ Building - AI Waifu Supremacy
|
|
42 |
- NurtureAI
|
43 |
(For open sourcing data to be used for fine tuning)
|
44 |
- NobodyExistsOnTheInternet
|
45 |
-
- unalignment
|
|
|
|
|
|
|
|
21 |
|
22 |
## Datasets used:
|
23 |
|
24 |
+
- unalignment/toxic-dpo-v0.2
|
25 |
+
- NobodyExistsOnTheInternet/ToxicQAFinal
|
26 |
+
- Open-Orca/SlimOrca (subset of data)
|
27 |
+
- PygmalionAI/PIPPA
|
28 |
+
- MinervaAI/Aesir-Preview
|
29 |
|
30 |
### Model Description
|
31 |
|
|
|
45 |
- NurtureAI
|
46 |
(For open sourcing data to be used for fine tuning)
|
47 |
- NobodyExistsOnTheInternet
|
48 |
+
- unalignment
|
49 |
+
- Open-Orca
|
50 |
+
- PygmalionAI
|
51 |
+
- MinervaAI
|